test_parser.py

"""
Test script for the IIS log parser
"""

from log_parser import IISLogParser, LogAnalyzer
import time

def test_log_file(file_path: str):
    """Test parsing a single log file."""
    print(f"\n{'='*80}")
    print(f"Testing: {file_path}")
    print(f"{'='*80}")

    start_time = time.time()

    # Parse
    parser = IISLogParser(file_path)
    df = parser.parse()
    parse_time = time.time() - start_time
    print(f"Service Name: {parser.service_name}")
    print(f"✓ Parsed {df.height:,} log entries in {parse_time:.2f}s")

    # Analyze
    analyzer = LogAnalyzer(df, parser.service_name)
    stats = analyzer.get_summary_stats()

    analyze_time = time.time() - start_time - parse_time
    print(f"✓ Analyzed in {analyze_time:.2f}s")

    # Display summary
    print(f"\n📊 Summary Statistics:")
    print(f"  Total Requests (before): {stats['total_requests_before']:,}")
    print(f"  Excluded Requests: {stats['excluded_requests']:,}")
    print(f"  Total Requests (after): {stats['total_requests_after']:,}")
    print(f"  Errors (≠200,≠401): {stats['errors']:,}")
    print(f"  Slow Requests (>3s): {stats['slow_requests']:,}")
    print(f"  Peak RPS: {stats['peak_rps']:,} @ {stats['peak_timestamp']}")
    print(f"  Avg Response Time: {stats['avg_time_ms']:,}ms")
    print(f"  Max Response Time: {stats['max_time_ms']:,}ms")
    print(f"  Min Response Time: {stats['min_time_ms']:,}ms")

    # Top methods
    print(f"\n🔝 Top 5 Methods:")
    top_methods = analyzer.get_top_methods(5)
    for i, method in enumerate(top_methods, 1):
        print(f"  {i}. {method['method_name']}")
        print(f"     Count: {method['count']:,} | Avg Time: {method['avg_time']:.1f}ms | Errors: {method['errors']}")

    # Error breakdown
    errors = analyzer.get_error_breakdown()
    if errors:
        print(f"\n❌ Error Breakdown:")
        for error in errors:
            print(f"  Status {error['sc_status']}: {error['count']:,} occurrences")
    else:
        print(f"\n✓ No errors found!")

    # Errors by method
    errors_by_method = analyzer.get_errors_by_method(5)
    if errors_by_method:
        print(f"\n⚠️  Top 5 Error-Prone Methods:")
        for i, method_error in enumerate(errors_by_method, 1):
            print(f"  {i}. {method_error['full_method_path']}")
            print(f"     Total Calls: {method_error['total_calls']:,} | Errors: {method_error['error_count']:,} | "
                  f"Error Rate: {method_error['error_rate_percent']:.2f}% | "
                  f"Most Common Error: {method_error.get('most_common_error_status', 'N/A')}")
    else:
        print(f"\n✓ No method errors found!")

    # Response time distribution
    dist = analyzer.get_response_time_distribution()
    print(f"\n⏱️  Response Time Distribution:")
    for bucket, count in dist.items():
        print(f"  {bucket}: {count:,}")

    total_time = time.time() - start_time
    print(f"\n⏱️  Total processing time: {total_time:.2f}s")

    return stats


if __name__ == "__main__":
    import sys

    # Test with both log files
    files = [
        "administrator_rhr_ex250922.log",
        "customer_rhr_ex250922.log"
    ]

    all_stats = []
    total_start = time.time()

    for file_path in files:
        try:
            stats = test_log_file(file_path)
            all_stats.append(stats)
        except Exception as e:
            print(f"\n❌ Error processing {file_path}: {e}")
            import traceback
            traceback.print_exc()

    # Combined summary
    if len(all_stats) > 1:
        print(f"\n{'='*80}")
        print(f"COMBINED STATISTICS")
        print(f"{'='*80}")
        total_requests = sum(s['total_requests_after'] for s in all_stats)
        total_errors = sum(s['errors'] for s in all_stats)
        total_slow = sum(s['slow_requests'] for s in all_stats)

        print(f"Total Requests (all services): {total_requests:,}")
        print(f"Total Errors (all services): {total_errors:,}")
        print(f"Total Slow Requests (all services): {total_slow:,}")

    total_elapsed = time.time() - total_start
    print(f"\n⏱️  Total elapsed time: {total_elapsed:.2f}s")
    print(f"\n✓ All tests completed successfully!")